metadata
tags:
- generated_from_trainer
datasets:
- soda-clip-loader
model-index:
- name: soda-clip-finetuned
results: []
soda-clip-finetuned
This model was trained from scratch on the soda-clip-loader dataset. It achieves the following results on the evaluation set:
- Loss: 4.8565
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.8557 | 0.15 | 100 | 4.8520 |
| 4.852 | 0.29 | 200 | 4.8520 |
| 4.8526 | 0.44 | 300 | 4.8522 |
| 4.8521 | 0.59 | 400 | 4.8520 |
| 4.852 | 0.74 | 500 | 4.8520 |
| 4.852 | 0.88 | 600 | 4.8520 |
| 4.852 | 1.03 | 700 | 4.8520 |
| 4.8519 | 1.18 | 800 | 4.8542 |
| 4.8522 | 1.33 | 900 | 4.8520 |
| 4.852 | 1.47 | 1000 | 4.8520 |
| 4.852 | 1.62 | 1100 | 4.8520 |
| 4.852 | 1.77 | 1200 | 4.8520 |
| 4.852 | 1.92 | 1300 | 4.8520 |
| 4.852 | 2.06 | 1400 | 4.8520 |
| 4.852 | 2.21 | 1500 | 4.8520 |
| 4.852 | 2.36 | 1600 | 4.8520 |
| 4.852 | 2.51 | 1700 | 4.8520 |
| 4.852 | 2.65 | 1800 | 4.8520 |
| 4.852 | 2.8 | 1900 | 4.8520 |
| 4.852 | 2.95 | 2000 | 4.8522 |
| 4.852 | 3.1 | 2100 | 4.8521 |
| 4.852 | 3.24 | 2200 | 4.8521 |
| 4.8519 | 3.39 | 2300 | 4.8523 |
| 4.8521 | 3.54 | 2400 | 4.8521 |
| 4.852 | 3.69 | 2500 | 4.8521 |
| 4.8517 | 3.83 | 2600 | 4.8521 |
| 4.852 | 3.98 | 2700 | 4.8520 |
| 4.852 | 4.13 | 2800 | 4.8520 |
| 4.852 | 4.28 | 2900 | 4.8520 |
| 4.852 | 4.42 | 3000 | 4.8520 |
| 4.8519 | 4.57 | 3100 | 4.8523 |
| 4.8515 | 4.72 | 3200 | 4.8528 |
| 4.851 | 4.87 | 3300 | 4.8565 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2